Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -it
    -0.07
     יע
    -0.07
     formed
    -0.07
    ڷ
    -0.06
    ⍢
    -0.06
     për
    -0.06
     macht
    -0.06
    fb
    -0.06
    揭露
    -0.06
    衮
    -0.06
    POSITIVE LOGITS
    "][
    0.08
    最後
    0.08
    럼
    0.07
     }//
    0.07
    rocket
    0.07
    ›
    0.07
    _BASE
    0.07
    (':',
    0.07
    _score
    0.07
    报道称
    0.06
    Act Density 0.081%

    No Known Activations